The REPU CS’ Spanish–Quechua Submission to the AmericasNLP 2021 Shared Task on Open Machine Translation
Óscar Julián Cuesta Moreno
Abstract
We present the submission of REPUcs 1 to the AmericasNLP machine translation shared task for the low resource language pair Spanish-Quechua. Our neural machine translation system ranked first in Track two (development set not used for training) and third in Track one (training includes development data). Our contribution is focused on: (i) the collection of new parallel data from different web sources (poems, lyrics, lexicons, handbooks), and (ii) using large Spanish-English data for pre-training and then fine-tuning the Spanish-Quechua system. This paper describes the new parallel corpora and our approach in detail.
Topics & Concepts
Machine translationComputer scienceTask (project management)Machine translation systemNatural language processingArtificial intelligenceTraining setTrack (disk drive)LyricsSet (abstract data type)World Wide WebProgramming languageEngineeringOperating systemArtSystems engineeringLiteratureNatural Language Processing TechniquesTopic ModelingMultimodal Machine Learning Applications